{"id":"https://openalex.org/W4392904255","doi":"https://doi.org/10.1109/icassp48485.2024.10447699","title":"Adversarial Speech for Voice Privacy Protection from Personalized Speech Generation","display_name":"Adversarial Speech for Voice Privacy Protection from Personalized Speech Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904255","doi":"https://doi.org/10.1109/icassp48485.2024.10447699"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055000437","display_name":"Shihao Chen","orcid":"https://orcid.org/0000-0001-7646-8003"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shihao Chen","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,China","NERC-SLIP, University of Science and Technology of China (USTC), China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430201","display_name":"Liping Chen","orcid":"https://orcid.org/0009-0003-6453-5645"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Chen","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,China","NERC-SLIP, University of Science and Technology of China (USTC), China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,China","NERC-SLIP, University of Science and Technology of China (USTC), China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045487306","display_name":"KongAik Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"KongAik Lee","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Ling","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,China","NERC-SLIP, University of Science and Technology of China (USTC), China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110935514","display_name":"Lirong Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,China","NERC-SLIP, University of Science and Technology of China (USTC), China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055000437"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.6799,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.93529836,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11411","last_page":"11415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8147634267807007},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7811633944511414},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6808520555496216},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6185774803161621},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5772365927696228},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5743497610092163},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5472247004508972},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5436157584190369},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.46024104952812195},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43076950311660767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3450104594230652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8147634267807007},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7811633944511414},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6808520555496216},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6185774803161621},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5772365927696228},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5743497610092163},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5472247004508972},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5436157584190369},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.46024104952812195},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43076950311660767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3450104594230652},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1945616565","https://openalex.org/W2144404214","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2808631503","https://openalex.org/W2962747881","https://openalex.org/W2962788625","https://openalex.org/W2963542245","https://openalex.org/W2972359262","https://openalex.org/W2972706975","https://openalex.org/W2998572311","https://openalex.org/W3024869864","https://openalex.org/W3090254849","https://openalex.org/W3092028330","https://openalex.org/W3095410713","https://openalex.org/W3098557217","https://openalex.org/W3162158711","https://openalex.org/W3162258435","https://openalex.org/W3173715137","https://openalex.org/W4312914048","https://openalex.org/W4315778510","https://openalex.org/W4372260053","https://openalex.org/W4381198892","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6688816777","https://openalex.org/W6769178842","https://openalex.org/W6772349387","https://openalex.org/W6783527727","https://openalex.org/W6783867762","https://openalex.org/W6805710207"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W1546240199","https://openalex.org/W4397292310","https://openalex.org/W1976952689","https://openalex.org/W642007152","https://openalex.org/W2056066842","https://openalex.org/W596245619","https://openalex.org/W2008120082","https://openalex.org/W2184127972","https://openalex.org/W2320148263"],"abstract_inverted_index":{"The":[0,54],"rapid":[1],"progress":[2],"in":[3,19,30,34,100,152,170],"personalized":[4,9],"speech":[5,25,58,65,69,92,99,115,160],"generation":[6,70,93],"technology,":[7],"including":[8],"text-to-speech":[10],"(TTS)":[11],"and":[12,23,94],"voice":[13,77,121],"conversion":[14],"(VC),":[15],"poses":[16],"a":[17,46],"challenge":[18],"distinguishing":[20],"between":[21],"generated":[22,114],"real":[24],"for":[26,91],"human":[27],"listeners,":[28],"resulting":[29],"an":[31],"urgent":[32],"demand":[33],"protecting":[35],"speakers'":[36],"voices":[37],"from":[38,157],"malicious":[39],"misuse.":[40],"In":[41],"this":[42],"regard,":[43],"we":[44,84,129],"propose":[45],"speaker":[47,105,133],"protection":[48,122],"method":[49,56],"based":[50],"on":[51,112],"adversarial":[52,143,148],"attacks.":[53],"proposed":[55],"perturbs":[57],"signals":[59],"by":[60],"minimally":[61],"altering":[62],"the":[63,76,79,86,96,101,113,117,120,132,136,140,147,154,159,162],"original":[64],"while":[66],"rendering":[67],"downstream":[68],"models":[71],"unable":[72],"to":[73],"accurately":[74],"generate":[75],"of":[78,119,135,161],"target":[80,97,163],"speaker.":[81,164],"For":[82],"validation,":[83],"employ":[85],"open-source":[87],"pre-trained":[88],"YourTTS":[89,137,155],"model":[90,138,156],"protect":[95],"speaker's":[98],"white-box":[102],"scenario.":[103],"Automatic":[104],"verification":[106],"(ASV)":[107],"evaluations":[108],"were":[109],"carried":[110],"out":[111],"as":[116],"assessment":[118],"capability.":[123],"Our":[124],"experimental":[125],"results":[126],"show":[127],"that":[128],"successfully":[130],"perturbed":[131],"encoder":[134],"using":[139],"gradient-based":[141],"I-FGSM":[142],"perturbation":[144,149],"method.":[145],"Furthermore,":[146],"is":[150],"effective":[151],"preventing":[153],"generating":[158],"Audio":[165],"samples":[166],"can":[167],"be":[168],"found":[169],"https://voiceprivacy.github.io/Adeversarial-Speech-with-YourTTS.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2024-03-19T00:00:00"}
